Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Speeding up LLM inference with speculative decoding v1.0.0

Use this resource to speed up language model inference without changing its architecture

New

  • 353 downloads
  • 159 likes
  • 190 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install speculative-decoding-inference

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent sets up the technique that fits your constraints: draft model, Medusa heads or lookahead decoding. You get installation steps, a generation example and the speedup range given by the skill, 1.5 to 3.6×.

Mostly picked by

Updated November 2, 2026

Card for the “Speeding up LLM inference with speculative decoding” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: when to use it, installation and draft-model quick start
  • references/medusa.md and references/lookahead.md: Medusa decoding heads and lookahead decoding

Good fit for

  • You want lower latency for a chatbot or code generation
  • You deploy a model on limited hardware

Not for

    Tags

    • llm
    • inference
    • speculative decoding
    • latency

    About

    You say

    “Set up speculative decoding for my self-hosted model to reduce latency.”

    Card for the “Speeding up LLM inference with speculative decoding” skill

    Skill published by davila7 under the MIT license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to speed up language model inference without changing its architecture
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.6 KB
    • references/lookahead.md9 KB
    • references/medusa.md10 KB
    • SKILL.md14.2 KB

    Origin and licence

    Listed unmodified

    Author
    davila7
    Source
    github.com/davila7/claude-code-templates/tree/f57964ebda91cdfb31755661ecea9395f30020f1/cli-tool/components/skills/ai-research/emerging-techniques-speculative-decoding
    Licence
    MIT

    Notice

    « emerging-techniques-speculative-decoding » (davila7, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.